Publication number | US8209156 B2 |

Publication type | Grant |

Application number | US 12/314,847 |

Publication date | 26 Jun 2012 |

Filing date | 17 Dec 2008 |

Priority date | 8 Apr 2005 |

Fee status | Paid |

Also published as | US20090132216 |

Publication number | 12314847, 314847, US 8209156 B2, US 8209156B2, US-B2-8209156, US8209156 B2, US8209156B2 |

Inventors | Anthony J. Grichnik, Michael X. Seskin, James R. Mason, Timothy J. Felty |

Original Assignee | Caterpillar Inc. |

Export Citation | BiBTeX, EndNote, RefMan |

Patent Citations (160), Non-Patent Citations (38), Referenced by (5), Classifications (9), Legal Events (2) | |

External Links: USPTO, USPTO Assignment, Espacenet | |

US 8209156 B2

Abstract

A method is provided for designing a product. The method may include obtaining data records relating to one or more input variables and one or more output parameters associated with the product and selecting one or more input parameters from the one or more input variables. The method may also include generating a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records and providing a set of constraints to the computational model representative of a compliance state for the product. Further the method may include using the computational model and the provided set of constraints to generate statistical distributions for the one or more output parameters. The one or more input parameters and the one or more output parameters represent a design for the product.

Claims(20)

1. A computer-implemented method for designing a product, comprising:

obtaining data records relating to one or more input variables and one or more output parameters associated with the product;

selecting one or more input parameters from the one or more input variables;

generating a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records;

providing a set of constraints to the computational model representative of a compliance state for the product; and

using, by at least one processor, the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters based on an asymmetric random scatter process and the one or more output parameters, wherein the one or more input parameters and the one or more output parameters represent a design for the product.

2. The method of claim 1 , further including using the computational model to generate nominal values for the one or more input parameters and the one or more output parameters.

3. The method of claim 2 , further including modifying the design for the product by adjusting at least one of the statistical distributions and the nominal values for any of the one or more input parameters and the one or more output parameters.

4. The method of claim 1 , wherein using the computational model further includes:

obtaining respective ranges of the input parameters;

creating a plurality of scaled model data records based on the respective ranges of the input parameters;

determining a candidate set of values of scaled input parameters using the plurality of scaled model data records with a maximum zeta statistic multiplied by a process capability index C_{pk, min }using a genetic algorithm; and

determining the statistical distributions of the one or more input parameters based on the candidate set,

defining the zeta statistic ζ as:

wherein x _{i }represents a mean of an ith input, x _{j }represents the mean of a jth outcome, σ_{i }represents a standard deviation of the ith input, σ_{j }represents the standard deviation of the jth outcome, and |S_{ij}| represents sensitivity of the jth outcome to the ith input of the computational model,

defining the process capability index of the outcome least in control of the 1 . . . j outcomes under consideration, C_{pk, min}, as:

wherein USL,LSL represent upper and lower specification limits respectively of the jth outcome, x _{j }represents the mean or expected value of the jth outcome, and σ_{j }represents the standard deviation of the jth outcome.

5. The method of claim 4 , wherein the creating further includes:

scaling the respective ranges of the input parameters;

creating an initial central data record including corresponding to starting values of the scaled respective ranges of the input parameters;

randomly creating a plurality of sample data records of the input parameters within the scaled respective ranges of the input parameters;

creating a plurality of respective asymmetric random scatter (aSRS) data records of the plurality of sample data records as asymmetric scatter of the plurality of sample data records with respect to the initial central data record; and

creating the plurality of data records by combining the initial central data record, the sample data records, and the aSRS data records.

6. The method of claim 5 , wherein corresponding to starting values includes starting values that are derived from one or more of the boundaries of the computational model, probable solutions to the computational model, or a desired range produced by a previous symmetric random scatter (SRS) process or aSRS process.

7. The method of claim 4 , further including:

comparing the statistical distributions of the input parameters with the scaled respective ranges of input parameters; and

determining whether the statistical distributions of the input parameters match the scaled respective ranges of input parameters.

8. The method of claim 7 , further including:

if the statistical distributions of the input parameters do not match the scaled respective ranges of the input parameters, changing the scaled respective ranges of the input parameters to the same as the statistical distributions of the input parameters; and

re-determining the statistical distributions of the input parameters based on the changed scaled respective ranges until the statistical distributions of the input parameters match the scaled respective range of the input parameters.

9. The method of claim 8 , further including graphically displaying on a display:

the statistical distributions for the one or more input parameters and the one or more output parameters;

nominal values for the one or more input parameters and the one or more output parameters; and

statistical information for the one or more input parameters and the one or more output parameters obtained based on the data records.

10. A non-transitory computer readable medium storing a set of instructions for enabling a processor to:

obtain data records relating to one or more input variables and one or more output parameters associated with a product;

select one or more input parameters from the one or more input variables;

generate a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records;

provide a set of constraints to the computational model representative of a compliance state for the product; and

use the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters based on an asymmetric random scatter process and the one or more output parameters, wherein the one or more input parameters and the one or more output parameters represent a design for the product.

11. The computer readable medium of claim 10 , wherein the instructions for enabling the processor to use the computational model further enable the processor to:

obtain respective ranges of the input parameters;

create a plurality of scaled model data records based on the respective ranges of the input parameters;

determine a candidate set of values of scaled input parameters using the plurality of scaled model data records with a maximum zeta statistic multiplied by a process capability index C_{pk, min }using a genetic algorithm; and

determine the statistical distributions of the one or more input parameters based on the candidate set,

define the zeta statistic ζ as:

wherein x _{i }represents a mean of an ith input, x _{j }represents the mean of a jth outcome, σ_{i }represents a standard deviation of the ith input, σ_{j }represents the standard deviation of the jth outcome, and |S_{ij}| represents sensitivity of the jth outcome to the ith input of the computational model,

define the process capability index of the outcome least in control of the 1 . . . j outcomes under consideration, C_{pk, min}, as:

wherein USL,LSL represent upper and lower specification limits respectively of the jth outcome, x _{j }represents the mean or expected value of the jth outcome, and σ_{j }represents the standard deviation of the jth outcome.

12. The computer readable medium of claim 11 further including instructions for enabling the processor to:

scale the respective ranges of the input parameters;

create an initial central data record including corresponding to starting values of the scaled respective ranges of the input parameters;

randomly create a plurality of sample data records of the input parameters within the scaled respective ranges of the input parameters;

create a plurality of respective asymmetric random scatter (aSRS) data records of the plurality of sample data records as asymmetric scatter of the plurality of sample data records with respect to the initial central data record; and

create the plurality of data records by combining the initial central data record, the sample data records, and the aSRS data records.

13. The computer readable medium of claim 12 , wherein corresponding to starting values includes starting values that are derived from one or more of the boundaries of the computational model, probable solutions to the computational model, or a desired range produced by a previous symmetric random scatter (SRS) process or aSRS process.

14. The computer readable medium of claim 11 further including instructions for enabling the processor to:

compare the statistical distributions of the input parameters with the scaled respective ranges of input parameters; and

determine whether the statistical distributions of the input parameters match the scaled respective ranges of input parameters.

15. The computer readable medium of claim 11 further including instructions for enabling the processor to graphically display:

the statistical distributions for the one or more input parameters and the one or more output parameters;

nominal values for the one or more input parameters and the one or more output parameters; and

statistical information for the one or more input parameters and the one or more output parameters obtained based on the data records.

16. A computer-based product design system, comprising:

a database containing data records relating one or more input variables and one or more output parameters associated with a product to be designed; and

a processor configured to:

obtain data records relating to the one or more input variables and the one or more output parameters associated with the product;

select one or more input parameters from the one or more input variables;

generate a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records;

provide a set of constraints to the computational model representative of a compliance state for the product; and

use the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters based on an asymmetric random scatter process and the one or more output parameters, wherein the one or more input parameters and the one or more output parameters represent a design for the product.

17. The computer-based product design system of claim 16 , wherein to use the computational model to generate statistical distributions, the processor is further configured to:

obtain respective ranges of the input parameters;

create a plurality of scaled model data records based on the respective ranges of the input parameters;

determine a candidate set of values of scaled input parameters using the plurality of scaled model data records with a maximum zeta statistic multiplied by a process capability index C_{pk, min }using a genetic algorithm; and

determine the statistical distributions of the one or more input parameters based on the candidate set,

define the zeta statistic ζ as:

wherein x _{i }represents a mean of an ith input, x _{j }represents the mean of a jth outcome, σ_{i }represents a standard deviation of the ith input, σ_{j }represents the standard deviation of the jth outcome, and |S_{ij}| represents sensitivity of the jth outcome to the ith input of the computational model,

define the process capability index of the outcome least in control of the 1 . . . j outcomes under consideration, C_{pk, min}, as:

wherein USL,LSL represent upper and lower specification limits respectively of the jth outcome, x _{j }represents the mean or expected value of the jth outcome, and σ_{j }represents the standard deviation of the jth outcome.

18. The computer-based product design system of claim 17 , wherein to use the computational model to generate statistical distributions, the processor is further configured to:

scale the respective ranges of the input parameters;

create an initial central data record including corresponding to starting values of the scaled respective ranges of the input parameters;

randomly create a plurality of sample data records of the input parameters within the scaled respective ranges of the input parameters;

create a plurality of respective asymmetric random scatter (aSRS) data records of the plurality of sample data records as asymmetric scatter of the plurality of sample data records with respect to the initial central data record; and

create the plurality of data records by combining the initial central data record, the sample data records, and the aSRS data records.

19. The computer-based product design system of claim 18 , wherein corresponding to starting values includes starting values that are derived from one or more of the boundaries of the computational model, probable solutions to the computational model, or a desired range produced by a previous symmetric random scatter (SRS) process or aSRS process.

20. The computer-based product design system of claim 16 , further including:

a display;

wherein the processor is configured to display the statistical distributions for the one or more input parameters and the one or more output parameters;

nominal values for the one or more input parameters and the one or more output parameters; and

statistical information for the one or more input parameters and the one or more output parameters obtained based on the data records.

Description

This application is a continuation-in-part of U.S. patent application Ser. No. 11/477,515, filed on Jun. 30, 2006, now U.S. Pat. No. 7,877,239 which is a continuation-in-part of U.S. patent application Ser. No. 11/101,498, filed on Apr. 8, 2005, now abandoned all of which are incorporated herein by reference.

This disclosure relates generally to product design systems and, more particularly, to probabilistic design based modeling systems for use in product design applications with asymmetric random scatter processing techniques.

Many computer-based applications exist for aiding in the design of products. Using these applications, an engineer can construct a computer model of a particular product and can analyze the behavior of the product through various analysis techniques. Further, certain analytical tools have been developed that enable engineers to evaluate and test multiple design configurations of a product. While these analytical tools may include internal optimization algorithms to provide this functionality, these tools generally represent only domain specific designs. Therefore, while product design variations can be tested and subsequently optimized, these design variations are typically optimized with respect to only a single requirement within a specific domain.

Finite element analysis (FEA) applications may fall into this domain specific category. With FEA applications, an engineer can test various product designs against requirements relating to stress and strain, vibration response, modal frequencies, and stability. Because the optimizing algorithms included in these FEA applications can optimize design parameters only with respect to a single requirement, however, multiple design requirements must be transformed into a single function for optimization. For example, in FEA analysis, one objective may be to parameterize a product design such that stress and strain are minimized. Because the FEA software cannot optimize both stress and strain simultaneously, the stress and strain design requirements may be transformed into a ratio of stress to strain (i.e., the modulus of elasticity). In the analysis, this ratio becomes the goal function to be optimized.

Several drawbacks result from this approach. For example, because more than one output requirement is transformed into a single goal function, the underlying relationships and interactions between the design parameters and the response of the product system are hidden from the design engineer. Further, based on this approach, engineers may be unable to optimize their designs according to competing requirements.

Thus, there is a need for modeling and analysis applications that can establish heuristic models between design inputs and outputs, subject to defined constraints, and optimize the inputs such that the probability of compliance of multiple competing outputs is maximized. There is also a need for applications that can explain the causal relationship between design inputs and outputs. Further, there is a need for applications that can collect desired patterns of design inputs to reduce computational load required by the optimization. Additionally, there is a need for applications that may allow for high fidelity of the model near one or more boundary conditions of the design parameters.

Certain applications have been developed that attempt to optimize design inputs based on multiple competing outputs. For example, U.S. Pat. No. 6,086,617 (“the '617 patent”) issued to Waldon et al. on Jul. 11, 2000, describes an optimization design system that includes a directed heuristic search (DHS). The DHS directs a design optimization process that implements a user's selections and directions. The DHS also directs the order and directions in which the search for an optimal design is conducted and how the search sequences through potential design solutions.

While the optimization design system of the '617 patent may provide a multi-disciplinary solution for product design optimization, this system has several shortcomings. The efficiency of this system is hindered by the need to pass through slow simulation tools in order to generate each new model result. Further, there is no knowledge in the system model of how variation in the input parameters relates to variation in the output parameters. The system of the '617 patent provides only single point solutions, which may be inadequate especially where a single point optimum may be unstable when subject to variability introduced by a manufacturing process or other sources. Further, the system of the '617 patent is limited in the number of dimensions that can be simultaneously optimized and searched. Additionally, the '617 patent does not provide for high fidelity or scaled solutions near boundary conditions of the input parameters.

Methods and systems consistent with certain features of the disclosed systems are directed to improvements in the existing technology.

One aspect of the present disclosure includes a method for designing a product. The method may include obtaining data records relating to one or more input variables and one or more output parameters associated with the product and selecting one or more input parameters from the one or more input variables. The method may also include generating a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records and providing a set of constraints to the computational model representative of a compliance state for the product. Further the method may include using the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters based on an asymmetric random scatter process and the one or more output parameters. The one or more input parameters and the one or more output parameters may represent a design for the product.

Another aspect of the present disclosure includes a computer readable medium. The computer readable medium may include a set of instructions for enabling a processor to obtain data records relating to one or more input variables and one or more output parameters associated with a product and to select one or more input parameters from the one or more input variables. The set of instructions may also enable the processor to generate a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records and to provide a set of constraints to the computational model representative of a compliance state for the product. Further, the set of instructions may enable the processor to use the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters based on an asymmetric random scatter process and the one or more output parameters. The one or more input parameters and the one or more output parameters may represent a design for the product.

Another aspect of the present disclosure includes a computer-based product design system. The design system may include a database containing data records relating one or more input variables and one or more output parameters associated with a product to be designed and a processor. The processor may be configured to obtain data records relating to one or more input variables and one or more output parameters associated with the product and to select one or more input parameters from the one or more input variables. The processor may also be configured to generate a computational model indicative of interrelationships between the one or more input parameters and the one or more output parameters based on the data records and to provide a set of constraints to the computational model representative of a compliance state for the product. Further, the processor may be configured to use the computational model and the provided set of constraints to generate statistical distributions for the one or more input parameters based on an asymmetric random scatter process and the one or more output parameters. The one or more input parameters and the one or more output parameters represent a design for the product.

Reference will now be made in detail to exemplary embodiments, which are illustrated in the accompanying drawings. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts.

**100** for generating a design of a product. A product may refer to any entity that includes at least one part or component. A product may also refer to multiple parts assembled together to form an assembly. Non-limiting examples of products include machines, engines, automobiles, aircraft, boats, appliances, electronics, and any sub-components, sub-assemblies, or parts thereof.

A product design may be represented as a set of one or more input parameter values. These parameters may correspond to dimensions, tolerances, moments of inertia, mass, material selections, or any other characteristic affecting one or more properties of the product. The disclosed product design system **100** may be configured to provide a probabilistic product design such that one or more input parameters can be expressed as nominal values and corresponding statistical distributions. Similarly, the product design may include nominal values for one or more output parameters and corresponding statistical distributions. The statistical distributions of the output parameters may provide an indication of the probability that the product design complies with a desired set of output requirements. The statistical distribution may be one sided, such as in a unilateral tolerance, where the nominal value may vary in only one direction.

Product design system **100** may include a processor **102**, a memory module **104**, a database **106**, an I/O interface **108**, and a network interface **110**. Product design system **100** may also include a display **112**. Any other components suitable for receiving and interacting with data, executing instructions, communicating with one or more external workstations, displaying information, etc. may also be included in product design system **100**.

Processor **102** may include any appropriate type of general purpose microprocessor, digital signal processor, or microcontroller. Memory module **104** may include one or more memory devices including, but not limited to, a ROM, a flash memory, a dynamic RAM, and a static RAM. Memory module **104** may be configured to store information accessed and used by processor **102**. Database **106** may include any type of appropriate database containing information relating to characteristics of input parameters, output parameters, mathematical models, and/or any other control information. I/O interface **108** may be connected to various data input devices (e.g., keyboards, pointers, drawing tablets, etc.) (not shown) to provide data and control information to product design system **100**. Network interface **110** may include any appropriate type of network adaptor capable of communicating with other computer systems based on one or more communication protocols. Display **112** may include any type of device (e.g., CRT monitors, LCD screens, etc.) capable of graphically depicting information.

**100**. At step **202**, product design system may obtain data records relating to input variables and output parameters associated with a product to be designed. The data records may reflect characteristics of the input parameters and output parameters, such as statistical distributions, normal ranges, and/or tolerances, etc. For each data record, there may be a set of output parameter values that corresponds to a particular set of input variable values. The data records may represent pre-generated data that has been stored, for example, in database **106**. The data may be computer generated or empirically collected through testing of actual products.

In one embodiment, the data records may be generated in the following manner. For a particular product to be designed, a design space of interest may be identified. A plurality of sets of random values may be generated for various input variables that fall within the desired product design space. These sets of random values may be supplied to at least one simulation algorithm to generate values for one or more output parameters related to the input variables. The at least one simulation algorithm may be associated with, for example, systems for performing finite element analysis, computational fluid dynamics analysis, radio frequency simulation, electromagnetic field simulation, electrostatic discharge simulation, network propagation simulation, discrete event simulation, constraint-based network simulation, or any other appropriate type of dynamic simulation.

At step **204**, which may be optional, the data records may be pre-processed. Processor **102** may pre-process the data records to clean up the data records for obvious errors and to eliminate redundancies. Processor **102** may remove approximately identical data records and/or remove data records that are out of a reasonable range in order to be meaningful for model generation and optimization. For randomly generated data records, any cases violating variable covariance terms may be eliminated. After the data records have been pre-processed, processor **102** may then select proper input parameters at step **206** by analyzing the data records.

The data records may include many input variables. In certain situations, for example, where the data records are obtained through experimental observations, the number of input variables may exceed the number of the data records and lead to sparse data scenarios. In these situations, the number of input variables may need to be reduced to create mathematical models within practical computational time limits and that contain enough degrees of freedom to map the relationship between inputs and outputs. In certain other situations, however, where the data records are computer generated using domain specific algorithms, there may be less of a risk that the number of input variables exceeds the number of data records. That is, in these situations, if the number of input variables exceeds the number of data records, more data records may be generated using the domain specific algorithms. Thus, for computer generated data records, the number of data records can be made to exceed, and often far exceed, the number of input variables. For these situations, the input parameters selected for use in step **206** may correspond to the entire set of input variables.

Where the number on input variables exceeds the number of data records, and it would not be practical or cost-effective to generate additional data records, processor **102** may select input parameters at step **206** according to predetermined criteria. For example, processor **102** may choose input parameters by experimentation and/or expert opinions. Alternatively, in certain embodiments, processor **102** may select input parameters based on a Mahalanobis distance between a normal data set and an abnormal data set of the data records. The normal data set and abnormal data set may be defined by processor **102** by any suitable method. For example, the normal data set may include characteristic data associated with the input parameters that produce desired output parameters. On the other hand, the abnormal data set may include any characteristic data that may be out of tolerance or may need to be avoided. The normal data set and abnormal data set may be predefined by processor **102**.

Mahalanobis distance may refer to a mathematical representation that may be used to measure data profiles based on correlations between parameters in a data set. Mahalanobis distance differs from Euclidean distance in that Mahalanobis distance takes into account the correlations of the data set. The Mahalanobis distance of a row i of set X (e.g., a set of multivariate vectors) from the mean of set X may be represented as

MD_{i}=(*X* _{i}−μ_{x})Σ^{−1}(*X* _{i}−μ_{x})′ (1)

where μ_{x }is the mean of X and Σ^{−1 }is an inverse variance-covariance matrix of X. MD_{i }weights the distance of a data point X_{i }from its mean μ_{x }such that observations that are on the same multivariate normal density contour will have the same distance. Such observations may be used to identify and select correlated parameters from separate data groups having different variances.

Processor **102** may select a desired subset of input parameters such that the Mahalanobis distance between the normal data set and the abnormal data set is maximized or optimized. A genetic algorithm may be used by processor **102** to search the input parameters for the desired subset with the purpose of maximizing the Mahalanobis distance. Processor **102** may select a candidate subset of the input parameters based on a predetermined criteria and calculate a Mahalanobis distance MD_{normal }of the normal data set and a Mahalanobis distance MD_{abnormal }of the abnormal data set. Processor **102** may also calculate the Mahalanobis distance between the normal data set and the abnormal data (i.e., the deviation of the Mahalanobis distance MD_{x}=MD_{normal}−MD_{normal}). Other types of deviations, however, may also be used.

Processor **102** may select the candidate subset of the input parameters if the genetic algorithm converges (i.e., the genetic algorithm finds the maximized or optimized Mahalanobis distance between the normal data set and the abnormal data set corresponding to the candidate subset). If the genetic algorithm does not converge, a different candidate subset of the input parameters may be created for further searching. This searching process may continue until the genetic algorithm converges and a desired subset of the input parameters is selected.

After selecting input parameters, processor **102** may generate a computational model to build interrelationships between the input parameters and output parameters (step **208**). Any appropriate type of neural network may be used to build the computational model. The type of neural network models used may include back propagation, feed forward models, cascaded neural networks, and/or hybrid neural networks, etc. Particular types or structures of the neural network used may depend on particular applications. Other types of models, such as linear system or non-linear system models, etc., may also be used.

The neural network computational model may be trained by using selected data records. For example, the neural network computational model may include a relationship between output parameters (e.g., engine power, engine efficiency, engine vibration, etc.) and input parameters (e.g., cylinder wall thickness, cylinder wall material, cylinder bore, etc). The neural network computational model may be evaluated by predetermined criteria to determine whether the training is completed. The criteria may include desired ranges of accuracy, time, and/or number of training iterations, etc.

After the neural network has been trained (i.e., the computational model has initially been established based on the predetermined criteria), processor **102** may statistically validate the computational model (step **210**). Statistical validation may refer to an analyzing process to compare outputs of the neural network computational model with actual outputs to determine the accuracy of the computational model. Part of the data records may be reserved for use in the validation process. Alternatively, processor **102** may generate simulation or test data for use in the validation process.

Once trained and validated, the computational model may be used to determine values of output parameters when provided with values of input parameters. Further, processor **102** may optimize the model by determining desired distributions of the input parameters based on relationships between the input parameters and desired distributions of the output parameters (step **212**).

Processor **102** may analyze the relationships between distributions of the input parameters and desired distributions of the output parameters (e.g., design constraints provided to the model that may represent a state of compliance of the product design). Processor **102** may then run a simulation of the computational model to find statistical distributions for an individual input parameter. That is, processor **102** may separately determine a distribution (e.g., mean, standard variation, etc.) of the individual input parameter corresponding to the ranges of the output parameters representing a compliance state for the product. Processor **102** may then analyze and combine the desired distributions for all the individual input parameters to determined desired distributions and characteristics for the input parameters.

Alternatively, processor **102** may identify desired distributions of input parameters simultaneously to maximize the probability of obtaining desired outcomes (i.e., to maximize the probability that a certain product design is compliant with the desired requirements). In certain embodiments, processor **102** may simultaneously determine desired distributions of the input parameters based on zeta statistic. Zeta statistic may indicate a relationship between input parameters, their value ranges, and desired outcomes. Zeta statistic may be represented as

where _{i }represents the mean or expected value of an ith input; _{j }represents the mean or expected value of a jth outcome; σ_{i }represents the standard deviation of the ith input; σ_{j }represents the standard deviation of the jth outcome; and |S_{ij}| represents the partial derivative or sensitivity of the jth outcome to the ith input.

Processor **102** may identify a desired distribution of the input parameters such that the zeta statistic of the neural network computational model is maximized or optimized. A genetic algorithm may be used by processor **102** to search the desired distribution of input parameters with the purpose of maximizing the zeta statistic. Processor **102** may select a candidate set of input parameters with predetermined search ranges and run a simulation of the product design model to calculate the zeta statistic parameters based on the input parameters, the output parameters, and the neural network computational model. Processor **102** may obtain _{i }and σ_{i }by analyzing the candidate set of input parameters, and obtain _{j }and σ_{j }by analyzing the outcomes of the simulation. Further, processor **102** may obtain |S_{ij}| from the trained neural network as an indication of the impact of ith input on the jth outcome.

Although maximizing the zeta statistic may increase stability of the outcome in the face of variable inputs, it does not ensure that the outcome converges to an optimal solution. Incorporating the C_{pk, min }statistic may produce more robust outcomes and improve the optimization of the solution. The C_{pk, min }statistic may be represented as

where C_{pk,min }represents the process capability index, USL,LSL represent the upper and lower specification limits, respectively, of the jth outcome, _{j }represents the mean or expected value of a jth outcome, and σ_{j }represents the standard deviation of the jth outcome.

The zeta statistic multiplied by C_{pk, min }may serve as a goal function for the optimization, where C_{pk, min }is the process capability of the outcome that is least in control of the outcomes under consideration. It is desirable to maximize the zeta statistic multiplied by C_{pk, min}. The zeta statistic multiplied by C_{pk, min }may be a useful goal function, as it is stable and focuses on the inputs that most affect the outcomes. Least in control may be the lowest value for C_{pk, min}, and this lowest value drives the goal function. This approach may allow consideration of multiple input/outcome relationships simultaneously in the zeta statistic. The zeta statistic may provide for the possibility that a jth outcome may not vary over a portion of the ith variable range by allowing S_{ij}=0 for that portion of the range. In other words, to maximize the zeta function we want poor input control to produce consistent outcome control by focusing on only the most significant input/outcome relationships.

Processor **102** may select the candidate set of values of input parameters if the genetic algorithm converges (i.e., the genetic algorithm finds the maximized or optimized zeta statistic of the product design model corresponding to the candidate set of input parameters). If the genetic algorithm does not converge, a different candidate set of values of input parameters may be created by the genetic algorithm for further searching. This searching process may continue until the genetic algorithm converges and a desired set of values of the input parameters is identified. Processor **102** may further determine desired distributions (e.g., mean and standard deviations) of input parameters based on the desired set of values of input parameters.

In certain embodiments, processor **102** may perform a symmetric random scatter (SRS) process to decrease the amount of time that processor **102** spends on the above searching process. In other embodiments, processor **102** may perform an asymmetric random scatter (aSRS) process to decrease the amount of time that processor **102** spends on the above searching process.

The SRS process can be thought of as creating a set of symmetric seed points around a center point in the design space. The aSRS process can be thought of as creating the same percentage of points on each side of a center point in the design space. In some cases, such as when the boundaries of one or more inputs are asymmetric about the center point, an aSRS process may converge with less iterations than a SRS process.

A symmetric scatter, as used herein, may refer to a mathematical object resulted from a symmetric transformation of an original mathematic object. The original mathematic object may include any appropriate mathematical objects, such as polynomials, vectors, shapes, or discrete mathematical objects, etc. The symmetric transformation may include any appropriate type of mathematical operations, such as mirroring, geometrical transformation, or space/vector transformation, etc. A symmetric random scatter may refer to the symmetric scatter of a random original mathematical object. **102**.

An asymmetric scatter, as used herein, may refer to a mathematical object resulting from an asymmetric transformation of an original mathematic object. The original mathematical object is scaled, that is, the engineering units are converted to a range between minus one (−1) and one (1). The original mathematic object may include any appropriate mathematical objects, such as polynomials, vectors, shapes, or discrete mathematical objects, etc. The asymmetric transformation may include any appropriate type of mathematical operations, such as mirroring, geometrical transformation, or space/vector transformation, etc. An asymmetric random scatter may refer to the asymmetric scatter of a random original mathematical object. **102**.

As shown in **102** may obtain a starting range for each of the input parameters (step **302**). Processor **102** may obtain the starting range by analyzing the select data records of the input parameters. The processor **102** may also obtain the starting range from other applications or processes associated with the input parameters. After the starting range for each of the input parameters are obtained (step **302**), processor **102** may create a centroid data record of the input parameters (step **304**). The centroid data record may be a mean of the input parameters. The mean may include any appropriate mathematical mean of the input parameters, such as statistical mean, or geometric mean, etc. For example, the centroid data record may include a midpoint of each of the input parameters. Other types of means, however, may also be used.

The starting range of each input parameters may define an input space (i.e., all ranges or possible values of the input parameters), the centroid data record may then be referred to as a center of the input space. After the centroid data record is created (step **304**), processor **102** may create a plurality of sample data records within the starting range (step **306**). The sample data records may include any data record having a value for each input parameter from the starting range. Processor **102** may create the sample data records in various ways. In certain embodiments, the sample records may be created randomly by processor **102**. The total number of the sample data records may be predetermined base on a particular application. For example, a total of approximately 10 sample data records may be created for the applications described in this disclosure. Other numbers of sample data records, however, may also be used.

Further, processor **102** may create a corresponding plurality of SRS data records (step **308**). To create the SRS data records, processor **102** may calculate a SRS for each sample data record. That is, each sample data record may be an original mathematic object and the SRS of each sample data record may be a symmetric vector opposite of each original mathematic object (e.g., a vector) with respect to the centroid data record (e.g., the center of the input space). For example, an original two-dimensional vector (1,1) may have a symmetric scatter of (−1, −1) with respect to a centroid of (0, 0). Because the SRS data records may be symmetric scatters of the sample data records, the combination of the SRS data records, the sample data records, and the centroid data record may reflect a random part of the starting range centered at the mean of the input parameters.

After creating the plurality of SRS data records, processor **102** may use the SRS data records, the sample data records, and the centroid data record as the selected data records to perform the zeta statistic optimization as describe above (step **310**). Processor **102** may also generate a desired distribution or desired range of the input parameters from the zeta statistic optimization. Further, processor **102** may compare the starting range of the input parameters with the desired range of the input parameters (step **312**).

Processor **102** may determine whether the starting range matches with the desired range (step **314**). The criteria for determining whether or not the two ranges match may be different depending on the particular application. For example, processor **102** may determine a match if the two ranges match each other exactly. Or processor **102** may determine a match if the two ranges match each other within a predetermined error margin. Further, processor **102** may determine a match if the desired range covers the starting range, or the starting range covers the desired range, within a predetermined error margin. Other types of matching, however, may also be used.

If processor **102** determines that the desired range matches the starting range (step **314**; yes), processor **102** may complete the SRS process and continue with the designing process. On the other hand, if processor **102** determines that the desired range does not match the starting range (step **314**; no), processor **102** may use the desired range as the starting range in step **302** and continue the SRS process until the two ranges match or until a predetermined time period expires. In an alternate embodiment, if processor **102** determines that the desired range does not match the starting range (step **314**; no), processor **102** may begin an aSRS process until the two ranges match or until a predetermined time period expires. **400** depicting an exemplary aSRS process.

The aSRS process may perform many of the same steps as the SRS process, and those steps may not be described in full detail again where similar. As shown in **102** may obtain a starting range for each of the input parameters (step **402**). Processor **102** may obtain the starting range by analyzing the select data records of the input parameters. The processor **102** may also obtain the starting range from other applications or processes associated with the input parameters. After the starting range for each of the input parameters are obtained (step **402**), processor **102** may create an initial central data record of the input parameters (step **404**). The initial central data record may be a starting value for the input parameters. The starting value may be derived from the boundaries of the problem, probable solutions, sound engineering judgment, or as a desired range produced by a previous SRS process or a previous aSRS process. The initial central data record may not be in the center of the range of the input parameters. For example, the initial central data record may include a starting value of each of the input parameters. In one exemplary embodiment, the initial central data record may have starting values close to one or more boundaries of the input parameters, and not in the center or mean of the input ranges.

The starting range of each input parameters may define an input space (i.e., all ranges or possible values of the input parameters), the initial central data record may then be referred to as a center of the input space, even though technically it is not at the center of the input space. After the initial central data record is created (step **404**), processor **102** may scale each starting range for each of the input parameters centered around the starting value of each of the input parameters (step **406**). Scaling may comprise transforming the range between the lower boundary and the starting value of each input parameter to between minus one (−1) and zero (0). Scaling my further comprise transforming the range between the starting value of each input parameter and the upper boundary to between zero (0) and one (1). Scaling may cause each pair in the creation of a corresponding plurality of aSRS data records in step **410** to be an equal distance around the center of the input space in the scaled space. Scaling should make a matched pair of points around the center of the input space an equal percentage of distance to the boundary. For example, in a range of 800 rpm to 3000 rpm, where 1800 rpm is the center of the input space, scale 800 to 1800 rpm to −1 to 0, and scale 1800 to 3000 rpm from 0 to 1.

After scaling each starting range (step **406**), processor **102** may create a plurality of sample data records within the starting range (step **408**). Step **408** may be essentially the same as step **306**, and the details will not be repeated.

Further, processor **102** may create a corresponding plurality of aSRS data records (step **410**). The creation of aSRS data records is the same as the creation of SRS data records in step **308**, except the data records are created in the scaled input space. Because the aSRS data records may be symmetric scatters in the scaled input space of the sample data records, the combination of the aSRS data records, the sample data records, and the initial center data record may reflect a random part of the starting range centered at the mean of the scaled input parameters.

After creating the plurality of aSRS data records, processor **102** may use the aSRS data records, the sample data records, and the initial center data record as the selected data records to perform the zeta statistic optimization as describe above (step **412**). Processor **102** may also generate a desired distribution or desired range of the input parameters from the zeta statistic optimization.

Processor **102** may transform the scaled results of step **412** back into engineering units (step **414**). De-scaling may comprise transforming results at or below the initial center data point from minus one (−1) and zero (0) to the range between the lower boundary and the starting value of each input parameter. Scaling my further comprise transforming results at or above the initial center data point from zero (0) and one (1) to the range between the starting value of each input parameter and the upper boundary. Further, processor **102** may compare the starting range of the input parameters with the desired range of the input parameters (step **416**).

Processor **102** may determine whether the starting range matches with the desired range (step **416**). The criteria for determining whether or not the two ranges match may be different depending on the particular application. For example, processor **102** may determine a match if the two ranges match each other exactly. Or processor **102** may determine a match if the two ranges match each other within a predetermined error margin. Further, processor **102** may determine a match if the desired range covers the starting range, or the starting range covers the desired range, within a predetermined error margin. Other types of matching, however, may also be used.

If processor **102** determines that the desired range matches the starting range (step **418**; yes), processor **102** may complete the aSRS process and continue with the designing process. On the other hand, if processor **102** determines that the desired range does not match the starting range (step **418**; no), processor **102** may use the desired range as the starting range in step **402** and continue the aSRS process until the two ranges match or until a predetermined time period expires.

Returning to **212**), processor **102** may define a valid input space (step **214**) representative of an optimized design of the product. This valid input space may represent the nominal values and corresponding statistical distributions for each of the selected input parameters. To implement the design of the product, values for the input parameters selected within the valid input space would maximize the probability of achieving a compliance state according to the constraints provided to the model.

Once the valid input space has been determined, this information may be provided to display **112** (step **216**). Along with the input space information, the nominal values of the corresponding output parameters and the associated distributions may also be supplied to display **112**. Displaying this information conveys to the product design engineer the ranges of values for the selected input parameters that are consistent with the optimized product design. This information also enables the engineer to determine the probability of compliance of any one of or all of the output parameters in the optimized product design.

While the processor **102** may be configured to provide an optimized product design based on the interrelationships between the selected input parameters and the output parameters and on the selected output constraints, the model allows for additional input by the product design engineer. Specifically, at step **218**, the engineer is allowed to determine if the optimized product design generated by processor **102** represents the desired final design. If the answer is yes (step **218**, yes), then the process ends. If the answer is no (step **218**, no) the engineer can generate a design alternative (step **220**).

To generate a design alternative, the engineer can vary any of the values of the input parameters or the distributions associated with the input parameters. The changed values may be supplied back to the simulation portion of the model for re-optimization. Based on the changed values, the model will display updated values and distributions for the output parameters changed as a result of the change to the input parameters. From the updated information, the engineer can determine how the alternative product design impacts the probability of compliance. This process can continue until the engineer decides on a final product design. It should be noted that alternative designs may also be generated by varying the values or distributions for the output parameters or by defining different or additional product design constraints.

Display **112** may also be used to display statistical information relating to the performance of the product design model. For example, distributions for the input parameters and the output parameters may be calculated based on the original data records. These distributions may represent an actual statistical space that can be compared with a predicted statistical space generated by the model. Overlap of the actual statistical space with the predicted statistical space may indicate that the model is functioning as expected.

The disclosed systems and methods may efficiently provide optimized product designs for any type of product that can be modeled by computer. Based on the disclosed system, complex interrelationships may be analyzed during the generation of computational models to optimize the models by identifying distributions of input parameters to the models to obtain desired outputs. The robustness and accuracy of product designs may be significantly improved by using the disclosed systems and methods.

The efficiency of designing a product may also be improved using the disclosed systems and methods. For example, the disclosed zeta statistic approach yields knowledge of how variation in the input parameters translates to variation in the output parameters. Thus, by defining the interrelationships between the input parameters and the output parameters in a system, the disclosed product design system can operate based on a proxy concept. That is, because these interrelationships are known and modeled, there is no need to use domain specific algorithm tools each time the model wishes to explore the effects of a variation in value or distribution of an input parameter or output parameter. Thus, unlike traditional systems that must pass repeatedly pass through slow simulations as part of a design optimization process, the disclosed modeling system takes advantage of well-validated models (e.g., neural network models) in place of slow simulations to more rapidly determine an optimized product design solution.

The disclosed product design system can significantly reduce the cost to manufacture a product. Based on the statistical output generated by the model, the model can indicate the ranges of input parameter values that can be used to achieve a compliance state. The product design engineer can exploit this information to vary certain input parameter values without significantly affecting the compliance state of the product design. That is, the manufacturing constraints for a particular product design may be made less restrictive without affecting (or at least significantly affecting) the overall compliance state of the design. Relaxing the manufacturing design constraints can simplify the manufacturing process for the product, which can lead to manufacturing cost savings.

The disclosed product design system can also enable a product design engineer to explore “what if” scenarios based on the optimized model. Because the interrelationships between input parameters and output parameters are known and understood by the model, the product designer can generate alternative designs based on the optimized product design to determine how one or more individual changes will affect the probability of compliance. While these design alternatives may move away from the optimized product design solution, this feature of the product design system can enable a product designer to adjust the design based on experience. Specifically, the product designer may recognize areas in the optimized model where certain manufacturing constraints may be relaxed to provide a cost savings, for example. By exploring the effect of the alternative design on product compliance probability, the designer can determine whether the potential cost savings of the alternative design would outweigh a potential reduction in probability of compliance.

The disclosed product design system can also enable a design engineer to collect a pattern of design candidates that gives an improved probability of modeling the design space in a minimum number of simulation or data collection operations based on the symmetric random scatter (SRS) process and/or the asymmetric random scatter (aSRS) process. The SRS process and/or the aSRS process may also be combined with other modeling or design applications to significantly reduce the order of design iterations. Asymmetric random scatter may be helpful for modeling cases where one or more tolerances are unilateral, as opposed to bilateral.

The disclosed product design system has several other advantages. For example, the use of genetic algorithms at various stages in the model avoids the need for a product designer to define the step size for variable changes. Further, the model has no limit to the number of dimensions that can be simultaneously optimized and searched.

Other embodiments, features, aspects, and principles of the disclosed exemplary systems will be apparent to those skilled in the art and may be implemented in various environments and systems.

Patent Citations

Cited Patent | Filing date | Publication date | Applicant | Title |
---|---|---|---|---|

US3316395 | 23 May 1963 | 25 Apr 1967 | Credit Corp Comp | Credit risk computer |

US4136329 | 12 May 1977 | 23 Jan 1979 | Transportation Logic Corporation | Engine condition-responsive shutdown and warning apparatus |

US4533900 | 8 Feb 1982 | 6 Aug 1985 | Bayerische Motoren Werke Aktiengesellschaft | Service-interval display for motor vehicles |

US5014220 | 6 Sep 1988 | 7 May 1991 | The Boeing Company | Reliability model generator |

US5163412 | 8 Nov 1991 | 17 Nov 1992 | Neutronics Enterprises, Inc. | Pollution control system for older vehicles |

US5262941 | 30 Mar 1990 | 16 Nov 1993 | Itt Corporation | Expert credit recommendation method and system |

US5341315 | 13 Mar 1992 | 23 Aug 1994 | Matsushita Electric Industrial Co., Ltd. | Test pattern generation device |

US5386373 | 5 Aug 1993 | 31 Jan 1995 | Pavilion Technologies, Inc. | Virtual continuous emission monitoring system with sensor validation |

US5434796 | 30 Jun 1993 | 18 Jul 1995 | Daylight Chemical Information Systems, Inc. | Method and apparatus for designing molecules with desired properties by evolving successive populations |

US5539638 | 5 Nov 1993 | 23 Jul 1996 | Pavilion Technologies, Inc. | Virtual emissions monitor for automobile |

US5548528 | 30 Jan 1995 | 20 Aug 1996 | Pavilion Technologies | Virtual continuous emission monitoring system |

US5561610 | 30 Jun 1994 | 1 Oct 1996 | Caterpillar Inc. | Method and apparatus for indicating a fault condition |

US5566091 | 30 Jun 1994 | 15 Oct 1996 | Caterpillar Inc. | Method and apparatus for machine health inference by comparing two like loaded components |

US5585553 | 28 Jul 1995 | 17 Dec 1996 | Caterpillar Inc. | Apparatus and method for diagnosing an engine using a boost pressure model |

US5594637 | 26 May 1993 | 14 Jan 1997 | Base Ten Systems, Inc. | System and method for assessing medical risk |

US5598076 | 4 Dec 1992 | 28 Jan 1997 | Siemens Aktiengesellschaft | Process for optimizing control parameters for a system having an actual behavior depending on the control parameters |

US5604306 | 28 Jul 1995 | 18 Feb 1997 | Caterpillar Inc. | Apparatus and method for detecting a plugged air filter on an engine |

US5604895 | 29 Sep 1995 | 18 Feb 1997 | Motorola Inc. | Method and apparatus for inserting computer code into a high level language (HLL) software model of an electrical circuit to monitor test coverage of the software model when exposed to test inputs |

US5608865 | 14 Mar 1995 | 4 Mar 1997 | Network Integrity, Inc. | Stand-in Computer file server providing fast recovery from computer file server failures |

US5666297 | 13 May 1994 | 9 Sep 1997 | Aspen Technology, Inc. | Plant simulation and optimization software apparatus and method using dual execution models |

US5682317 | 23 Jul 1996 | 28 Oct 1997 | Pavilion Technologies, Inc. | Virtual emissions monitor for automobile and associated control system |

US5698780 | 18 Sep 1996 | 16 Dec 1997 | Toyota Jidosha Kabushiki Kaisha | Method and apparatus for detecting a malfunction in an intake pressure sensor of an engine |

US5727128 | 8 May 1996 | 10 Mar 1998 | Fisher-Rosemount Systems, Inc. | System and method for automatically determining a set of variables for use in creating a process model |

US5750887 | 18 Nov 1996 | 12 May 1998 | Caterpillar Inc. | Method for determining a remaining life of engine oil |

US5752007 | 11 Mar 1996 | 12 May 1998 | Fisher-Rosemount Systems, Inc. | System and method using separators for developing training records for use in creating an empirical model of a process |

US5835902 | 2 Nov 1994 | 10 Nov 1998 | Jannarone; Robert J. | Concurrent learning and performance information processing system |

US5842202 | 27 Nov 1996 | 24 Nov 1998 | Massachusetts Institute Of Technology | Systems and methods for data quality management |

US5914890 | 30 Oct 1997 | 22 Jun 1999 | Caterpillar Inc. | Method for determining the condition of engine oil based on soot modeling |

US5925089 | 10 Jul 1997 | 20 Jul 1999 | Yamaha Hatsudoki Kabushiki Kaisha | Model-based control method and apparatus using inverse model |

US5950147 | 5 Jun 1997 | 7 Sep 1999 | Caterpillar Inc. | Method and apparatus for predicting a fault condition |

US5966312 | 7 Nov 1997 | 12 Oct 1999 | Advanced Micro Devices, Inc. | Method for monitoring and analyzing manufacturing processes using statistical simulation with single step feedback |

US5987976 | 12 Mar 1998 | 23 Nov 1999 | Caterpillar Inc. | Method for determining the condition of engine oil based on TBN modeling |

US6086617 * | 18 Jul 1997 | 11 Jul 2000 | Engineous Software, Inc. | User directed heuristic design optimization search |

US6092016 | 25 Jan 1999 | 18 Jul 2000 | Caterpillar, Inc. | Apparatus and method for diagnosing an engine using an exhaust temperature model |

US6119074 | 20 May 1998 | 12 Sep 2000 | Caterpillar Inc. | Method and apparatus of predicting a fault condition |

US6145066 | 14 Nov 1997 | 7 Nov 2000 | Amdahl Corporation | Computer system with transparent data migration between storage volumes |

US6195648 | 10 Aug 1999 | 27 Feb 2001 | Frank Simon | Loan repay enforcement system |

US6199007 | 18 Apr 2000 | 6 Mar 2001 | Caterpillar Inc. | Method and system for determining an absolute power loss condition in an internal combustion engine |

US6208982 | 30 Jul 1997 | 27 Mar 2001 | Lockheed Martin Energy Research Corporation | Method and apparatus for solving complex and computationally intensive inverse problems in real-time |

US6223133 | 14 May 1999 | 24 Apr 2001 | Exxon Research And Engineering Company | Method for optimizing multivariate calibrations |

US6236908 | 7 May 1997 | 22 May 2001 | Ford Global Technologies, Inc. | Virtual vehicle sensors based on neural networks trained using data generated by simulation models |

US6240343 | 28 Dec 1998 | 29 May 2001 | Caterpillar Inc. | Apparatus and method for diagnosing an engine using computer based models in combination with a neural network |

US6269351 | 31 Mar 1999 | 31 Jul 2001 | Dryken Technologies, Inc. | Method and system for training an artificial neural network |

US6298718 | 8 Mar 2000 | 9 Oct 2001 | Cummins Engine Company, Inc. | Turbocharger compressor diagnostic system |

US6370544 | 17 Jun 1998 | 9 Apr 2002 | Itt Manufacturing Enterprises, Inc. | System and method for integrating enterprise management application with network management operations |

US6405122 | 2 Jun 1999 | 11 Jun 2002 | Yamaha Hatsudoki Kabushiki Kaisha | Method and apparatus for estimating data for engine control |

US6438430 | 9 May 2000 | 20 Aug 2002 | Pavilion Technologies, Inc. | Kiln thermal and combustion control |

US6442511 | 3 Sep 1999 | 27 Aug 2002 | Caterpillar Inc. | Method and apparatus for determining the severity of a trend toward an impending machine failure and responding to the same |

US6477660 | 3 Mar 1998 | 5 Nov 2002 | Sap Aktiengesellschaft | Data model for supply chain planning |

US6513018 | 5 May 1994 | 28 Jan 2003 | Fair, Isaac And Company, Inc. | Method and apparatus for scoring the likelihood of a desired performance result |

US6546379 | 26 Oct 1999 | 8 Apr 2003 | International Business Machines Corporation | Cascade boosting of predictive models |

US6584768 | 16 Nov 2000 | 1 Jul 2003 | The Majestic Companies, Ltd. | Vehicle exhaust filtration system and method |

US6594989 | 17 Mar 2000 | 22 Jul 2003 | Ford Global Technologies, Llc | Method and apparatus for enhancing fuel economy of a lean burn internal combustion engine |

US6698203 | 19 Mar 2002 | 2 Mar 2004 | Cummins, Inc. | System for estimating absolute boost pressure in a turbocharged internal combustion engine |

US6711676 | 15 Oct 2002 | 23 Mar 2004 | Zomaya Group, Inc. | System and method for providing computer upgrade information |

US6721606 | 24 Mar 2000 | 13 Apr 2004 | Yamaha Hatsudoki Kabushiki Kaisha | Method and apparatus for optimizing overall characteristics of device |

US6725208 | 12 Apr 1999 | 20 Apr 2004 | Pavilion Technologies, Inc. | Bayesian neural networks for optimization and control |

US6763708 | 31 Jul 2001 | 20 Jul 2004 | General Motors Corporation | Passive model-based EGR diagnostic |

US6775647 | 2 Mar 2000 | 10 Aug 2004 | American Technology & Services, Inc. | Method and system for estimating manufacturing costs |

US6785604 | 15 May 2002 | 31 Aug 2004 | Caterpillar Inc | Diagnostic systems for turbocharged engines |

US6810442 | 12 Sep 2001 | 26 Oct 2004 | Axis Systems, Inc. | Memory mapping system and method |

US6823675 | 13 Nov 2002 | 30 Nov 2004 | General Electric Company | Adaptive model-based control systems and methods for controlling a gas turbine |

US6859770 | 30 Nov 2000 | 22 Feb 2005 | Hewlett-Packard Development Company, L.P. | Method and apparatus for generating transaction-based stimulus for simulation of VLSI circuits using event coverage analysis |

US6859785 | 11 Jan 2001 | 22 Feb 2005 | Case Strategy Llp | Diagnostic method and apparatus for business growth strategy |

US6865883 | 12 Dec 2002 | 15 Mar 2005 | Detroit Diesel Corporation | System and method for regenerating exhaust system filtering and catalyst components |

US6882929 | 15 May 2002 | 19 Apr 2005 | Caterpillar Inc | NOx emission-control system using a virtual sensor |

US6895286 | 1 Dec 2000 | 17 May 2005 | Yamaha Hatsudoki Kabushiki Kaisha | Control system of optimizing the function of machine assembly using GA-Fuzzy inference |

US6935313 | 15 May 2002 | 30 Aug 2005 | Caterpillar Inc | System and method for diagnosing and calibrating internal combustion engines |

US6941287 | 17 Dec 1999 | 6 Sep 2005 | E. I. Du Pont De Nemours And Company | Distributed hierarchical evolutionary modeling and visualization of empirical data |

US6952662 | 12 Feb 2001 | 4 Oct 2005 | Smartsignal Corporation | Signal differentiation system using improved non-linear operator |

US6976062 | 18 Sep 2000 | 13 Dec 2005 | Intermec Ip Corp. | Automated software upgrade utility |

US7000229 | 24 Jul 2002 | 14 Feb 2006 | Sun Microsystems, Inc. | Method and system for live operating environment upgrades |

US7024343 | 30 Nov 2001 | 4 Apr 2006 | Visteon Global Technologies, Inc. | Method for calibrating a mathematical model |

US7027953 | 30 Dec 2002 | 11 Apr 2006 | Rsl Electronics Ltd. | Method and system for diagnostics and prognostics of a mechanical system |

US7035834 | 15 May 2002 | 25 Apr 2006 | Caterpillar Inc. | Engine control system using a cascaded neural network |

US7117079 | 5 Feb 2003 | 3 Oct 2006 | Cleaire Advanced Emission Controls, Llc | Apparatus and method for simultaneous monitoring, logging, and controlling of an industrial process |

US7124047 | 3 Sep 2004 | 17 Oct 2006 | Eaton Corporation | Mathematical model useful for determining and calibrating output of a linear sensor |

US7127892 | 13 Aug 2004 | 31 Oct 2006 | Cummins, Inc. | Techniques for determining turbocharger speed |

US7174284 | 21 Oct 2003 | 6 Feb 2007 | Siemens Aktiengesellschaft | Apparatus and method for simulation of the control and machine behavior of machine tools and production-line machines |

US7178328 | 20 Dec 2004 | 20 Feb 2007 | General Motors Corporation | System for controlling the urea supply to SCR catalysts |

US7191161 | 31 Jul 2003 | 13 Mar 2007 | The United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration | Method for constructing composite response surfaces by combining neural networks with polynominal interpolation or estimation techniques |

US7194392 | 23 Oct 2003 | 20 Mar 2007 | Taner Tuken | System for estimating model parameters |

US7213007 | 24 Dec 2002 | 1 May 2007 | Caterpillar Inc | Method for forecasting using a genetic algorithm |

US7356393 | 14 Nov 2003 | 8 Apr 2008 | Turfcentric, Inc. | Integrated system for routine maintenance of mechanized equipment |

US7369925 | 20 Jul 2005 | 6 May 2008 | Hitachi, Ltd. | Vehicle failure diagnosis apparatus and in-vehicle terminal for vehicle failure diagnosis |

US7787969 * | 15 Jun 2007 | 31 Aug 2010 | Caterpillar Inc | Virtual sensor system and method |

US7813869 * | 30 Mar 2007 | 12 Oct 2010 | Caterpillar Inc | Prediction based engine control system and method |

US8036764 * | 2 Nov 2007 | 11 Oct 2011 | Caterpillar Inc. | Virtual sensor network (VSN) system and method |

US20020014294 | 29 Jun 2001 | 7 Feb 2002 | The Yokohama Rubber Co., Ltd. | Shape design process of engineering products and pneumatic tire designed using the present design process |

US20020016701 | 6 Jul 2001 | 7 Feb 2002 | Emmanuel Duret | Method and system intended for real-time estimation of the flow mode of a multiphase fluid stream at all points of a pipe |

US20020042784 | 8 Oct 2001 | 11 Apr 2002 | Kerven David S. | System and method for automatically searching and analyzing intellectual property-related materials |

US20020049704 | 27 Apr 2001 | 25 Apr 2002 | Vanderveldt Ingrid V. | Method and system for dynamic data-mining and on-line communication of customized information |

US20020103996 | 31 Jan 2001 | 1 Aug 2002 | Levasseur Joshua T. | Method and system for installing an operating system |

US20020198821 | 21 Jun 2001 | 26 Dec 2002 | Rodrigo Munoz | Method and apparatus for matching risk to return |

US20030018503 | 19 Jul 2001 | 23 Jan 2003 | Shulman Ronald F. | Computer-based system and method for monitoring the profitability of a manufacturing plant |

US20030055607 | 7 Jun 2002 | 20 Mar 2003 | Wegerich Stephan W. | Residual signal alert generation for condition monitoring using approximated SPRT distribution |

US20030093250 | 8 Nov 2001 | 15 May 2003 | Goebel Kai Frank | System, method and computer product for incremental improvement of algorithm performance during algorithm development |

US20030126053 | 28 Dec 2001 | 3 Jul 2003 | Jonathan Boswell | System and method for pricing of a financial product or service using a waterfall tool |

US20030126103 | 24 Oct 2002 | 3 Jul 2003 | Ye Chen | Agent using detailed predictive model |

US20030130855 | 28 Dec 2001 | 10 Jul 2003 | Lucent Technologies Inc. | System and method for compressing a data table using models |

US20030167354 | 1 Mar 2002 | 4 Sep 2003 | Dell Products L.P. | Method and apparatus for automated operating systems upgrade |

US20030187567 | 28 Mar 2002 | 2 Oct 2003 | Saskatchewan Research Council | Neural control system and method for alternatively fueled engines |

US20030187584 | 28 Mar 2002 | 2 Oct 2003 | Harris Cole Coryell | Methods and devices relating to estimating classifier performance |

US20030200296 | 22 Apr 2002 | 23 Oct 2003 | Orillion Corporation | Apparatus and method for modeling, and storing within a database, services on a telecommunications network |

US20040030420 | 30 Jul 2002 | 12 Feb 2004 | Ulyanov Sergei V. | System and method for nonlinear dynamic control based on soft computing with discrete constraints |

US20040034857 | 19 Aug 2002 | 19 Feb 2004 | Mangino Kimberley Marie | System and method for simulating a discrete event process using business system data |

US20040059518 | 11 Sep 2003 | 25 Mar 2004 | Rothschild Walter Galeski | Systems and methods for statistical modeling of complex data sets |

US20040077966 | 18 Apr 2003 | 22 Apr 2004 | Fuji Xerox Co., Ltd. | Electroencephalogram diagnosis apparatus and method |

US20040122702 | 18 Dec 2002 | 24 Jun 2004 | Sabol John M. | Medical data processing system and method |

US20040122703 | 19 Dec 2002 | 24 Jun 2004 | Walker Matthew J. | Medical data operating model development system and method |

US20040128058 | 11 Jun 2003 | 1 Jul 2004 | Andres David J. | Engine control strategies |

US20040135677 | 26 Jun 2001 | 15 Jul 2004 | Robert Asam | Use of the data stored by a racing car positioning system for supporting computer-based simulation games |

US20040138995 | 15 Oct 2003 | 15 Jul 2004 | Fidelity National Financial, Inc. | Preparation of an advanced report for use in assessing credit worthiness of borrower |

US20040153227 | 15 Sep 2003 | 5 Aug 2004 | Takahide Hagiwara | Fuzzy controller with a reduced number of sensors |

US20040230404 | 25 Nov 2003 | 18 Nov 2004 | Messmer Richard Paul | System and method for optimizing simulation of a discrete event process using business system data |

US20040267818 | 18 Jun 2004 | 30 Dec 2004 | Hartenstine Troy A. | Collecting and valuating used items for sale |

US20050047661 | 27 Aug 2004 | 3 Mar 2005 | Maurer Donald E. | Distance sorting algorithm for matching patterns |

US20050055176 | 20 Aug 2004 | 10 Mar 2005 | Clarke Burton R. | Method of analyzing a product |

US20050091093 | 24 Oct 2003 | 28 Apr 2005 | Inernational Business Machines Corporation | End-to-end business process solution creation |

US20050209943 | 2 Mar 2005 | 22 Sep 2005 | Ballow John J | Enhanced business reporting methodology |

US20050210337 | 4 Mar 2004 | 22 Sep 2005 | Falconeer Technologies Llc | Method and system of monitoring, sensor validation and predictive fault analysis |

US20050240539 | 22 Apr 2004 | 27 Oct 2005 | Thomas Olavson | Method and system for forecasting commodity prices using capacity utilization data |

US20050261791 | 20 May 2004 | 24 Nov 2005 | Martin Chen | Interfaces from external systems to time dependent process parameters in integrated process and product engineering |

US20050262031 | 14 Mar 2005 | 24 Nov 2005 | Olivier Saidi | Systems and methods for treating, diagnosing and predicting the occurrence of a medical condition |

US20050278227 | 28 May 2004 | 15 Dec 2005 | Niel Esary | Systems and methods of managing price modeling data through closed-loop analytics |

US20050278432 | 14 Jun 2004 | 15 Dec 2005 | Feinleib David A | System and method for automated migration from windows to linux |

US20060010057 | 10 May 2005 | 12 Jan 2006 | Bradway Robert A | Systems and methods for conducting an interactive financial simulation |

US20060010142 | 28 Apr 2005 | 12 Jan 2006 | Microsoft Corporation | Modeling sequence and time series data in predictive analytics |

US20060010157 | 1 Mar 2005 | 12 Jan 2006 | Microsoft Corporation | Systems and methods to facilitate utilization of database modeling |

US20060025897 | 22 Aug 2005 | 2 Feb 2006 | Shostak Oleksandr T | Sensor assemblies |

US20060026270 | 1 Sep 2004 | 2 Feb 2006 | Microsoft Corporation | Automatic protocol migration when upgrading operating systems |

US20060026587 | 28 Jul 2005 | 2 Feb 2006 | Lemarroy Luis A | Systems and methods for operating system migration |

US20060064474 | 23 Sep 2004 | 23 Mar 2006 | Feinleib David A | System and method for automated migration from Linux to Windows |

US20060068973 | 27 Sep 2004 | 30 Mar 2006 | Todd Kappauf | Oxygen depletion sensing for a remote starting vehicle |

US20060129289 | 25 May 2005 | 15 Jun 2006 | Kumar Ajith K | System and method for managing emissions from mobile vehicles |

US20060130052 | 14 Dec 2004 | 15 Jun 2006 | Allen James P | Operating system migration with minimal storage area network reconfiguration |

US20060229753 | 8 Apr 2005 | 12 Oct 2006 | Caterpillar Inc. | Probabilistic modeling system for product design |

US20060229769 | 8 Apr 2005 | 12 Oct 2006 | Caterpillar Inc. | Control system and method |

US20060229852 | 8 Apr 2005 | 12 Oct 2006 | Caterpillar Inc. | Zeta statistic process method and system |

US20060229854 | 29 Jul 2005 | 12 Oct 2006 | Caterpillar Inc. | Computer system architecture for probabilistic modeling |

US20060230018 | 8 Apr 2005 | 12 Oct 2006 | Caterpillar Inc. | Mahalanobis distance genetic algorithm (MDGA) method and system |

US20060230097 | 8 Apr 2005 | 12 Oct 2006 | Caterpillar Inc. | Process model monitoring method and system |

US20060230313 | 8 Apr 2005 | 12 Oct 2006 | Caterpillar Inc. | Diagnostic and prognostic method and system |

US20060241923 | 2 May 2006 | 26 Oct 2006 | Capital One Financial Corporation | Automated systems and methods for generating statistical models |

US20060247798 | 28 Apr 2005 | 2 Nov 2006 | Subbu Rajesh V | Method and system for performing multi-objective predictive modeling, monitoring, and update for an asset |

US20070061144 | 30 Aug 2005 | 15 Mar 2007 | Caterpillar Inc. | Batch statistics process model method and system |

US20070094048 | 31 Jul 2006 | 26 Apr 2007 | Caterpillar Inc. | Expert knowledge combination process based medical risk stratifying method and system |

US20070094181 | 18 Sep 2006 | 26 Apr 2007 | Mci, Llc. | Artificial intelligence trending system |

US20070118338 | 18 Nov 2005 | 24 May 2007 | Caterpillar Inc. | Process model based virtual sensor and method |

US20070124237 | 30 Nov 2005 | 31 May 2007 | General Electric Company | System and method for optimizing cross-sell decisions for financial products |

US20070150332 | 22 Dec 2005 | 28 Jun 2007 | Caterpillar Inc. | Heuristic supply chain modeling method and system |

US20070168494 | 22 Dec 2005 | 19 Jul 2007 | Zhen Liu | Method and system for on-line performance modeling using inference for real production it systems |

US20070179769 | 25 Oct 2005 | 2 Aug 2007 | Caterpillar Inc. | Medical risk stratifying method and system |

US20070203864 | 31 Jan 2006 | 30 Aug 2007 | Caterpillar Inc. | Process model error correction method and system |

US20080154811 | 21 Dec 2006 | 26 Jun 2008 | Caterpillar Inc. | Method and system for verifying virtual sensors |

US20080201054 * | 29 Sep 2006 | 21 Aug 2008 | Caterpillar Inc. | Virtual sensor based engine control system and method |

US20090024367 | 17 Jul 2007 | 22 Jan 2009 | Caterpillar Inc. | Probabilistic modeling system for product design |

EP1103926B1 | 20 Sep 2000 | 5 Dec 2007 | General Electric Company | Methods and apparatus for model-based diagnostics |

EP1367248A1 | 27 Mar 2003 | 3 Dec 2003 | Caterpillar Inc. | NOx emission-control system using a virtual sensor |

EP1418481B1 | 31 Oct 2003 | 28 Dec 2005 | United Technologies Corporation | Method for performing gas turbine performance diagnostics |

Non-Patent Citations

Reference | ||
---|---|---|

1 | Allen et al., "Supersaturated Designs That Maximize the Probability of Identifying Active Factors," 2003 American Statistical Association and the American Society for Quality, Technometrics, vol. 45, No. 1, Feb. 2003, pp. 1-8. | |

2 | April, Jay et al., "Practical Introduction to Simulation Optimization," Proceedings of the 2003 Winter Simulation Conference, pp. 71-78. | |

3 | Bandte et al., "Viable Designs Through a Joint Probabilistic Estimation Technique," SAE International, and the American Institute of Aeronautics and Astronautics, Inc., Paper No. 1999-01-5623, 1999, pp. 1-11. | |

4 | Beisl et al., "Use of Genetic Algorithm to Identify the Source Point of Seepage Slick Clusters Interpreted from Radarsat-1 Images in the Gulf of Mexico," Geoscience and Remote Sensing Symposium, 2004, Proceedings, 2004 IEEE International Anchorage, AK, Sep. 20-24, 2004, vol. 6, pp. 4139-4142. | |

5 | Berke et al., "Optimum Design of Aerospace Structural Components Using Neural Networks," Computers and Structures, vol. 48, No. 6, Sep. 17, 1993, pp. 1001-1010. | |

6 | Bezdek, "Genetic Algorithm Guided Clustering," IEEE 0-7803-1899-4/94, 1994, pp. 34-39. | |

7 | Brahma et al., "Optimization of Diesel Engine Operating Parameters Using Neural Networks," SAE Technical Paper Series, 2003-01-3228, Oct. 27-30, 2003 (11 pages). | |

8 | Chau et al., "Use of runs test to access cardiovascular autonomic function in diabetic subjects," Abstract, Diabetes Care, vol. 17, Issue 2, pp. 146-148, available at http://care.diabetesjournals.org/cgi/content/abstract/17/2/146), 1994. | |

9 | Chung et al., "Process Optimal Design in Forging by Genetic Algorithm," Journal of Manufacturing Science and Engineering, vol. 124, May 2002, pp. 397-408. | |

10 | Cox et al., "Statistical Modeling for Efficient Parametric Yield Estimation of MOS VLSI Circuits," IEEE, 1983, pp. 242-245. | |

11 | De Maesschalck et al., "The Mahalanobis Distance," Chemometrics and Intelligent Laboratory Systems, vol. 50, No. 1, Jan. 2000, pp. 1-18. | |

12 | Dikmen et al., "Estimating Distributions in Genetic Algorithms," ISCIS 2003, LNCS 2869, 2003, pp. 521-528. | |

13 | Galperin, G., et al., "Parallel Monte-Carlo Simulation of Neural Network Controllers," available at http://www-fp.mcs.anl.gov/ccst/research/reports-pre1998/neural-network/galperin.html, printed Mar. 11, 2005 (6 pages). | |

14 | Galperin, G., et al., "Parallel Monte-Carlo Simulation of Neural Network Controllers," available at http://www-fp.mcs.anl.gov/ccst/research/reports—pre1998/neural—network/galperin.html, printed Mar. 11, 2005 (6 pages). | |

15 | Gletsos et al., "A Computer-Aided Diagnostic System to Characterize CT Focal Liver Lesions: Design and Optimization of a Neural Network Classifier," IEEE Transactions on InformationTechnology in Biomedicine, vol. 7, No. 3, Sep. 2003 pp. 153-162. | |

16 | * | Grichnik et al, "An Improved Metric for Robust Engineering", Proceedings of the 2007 International Conference on Scientific Computing, Las Vegas, NV, Jun. 25-28, 2007. |

17 | Grichnik et al., "An Improved Metric for Robust Engineering," Proceedings of the 2007 International Conference on Scientific Computing, Las Vegas, NV (4 pages). | |

18 | * | Grichnik, Anthony, An Improved Metric for Robust Engineering for WORLDCOMP2007, Jun. 18, 2007. |

19 | Holland, John H., "Genetic Algorithms," Scientific American, Jul. 1992, pp. 66-72. | |

20 | Hughes et al., "Linear Statistics for Zeros of Riemann's Zeta Function," C.R. Acad. Sci. Paris, Ser. I335 (2002), pp. 667-670. | |

21 | Ko et al., "Application of Artificial Neural Network and Taguchi Method to Perform Design in Metal Forming Considering Workability," International Journal of Machine Tools & Manufacture, vol. 39, No. 5, May 1999, pp. 771-785. | |

22 | Kroha et al., "Object Server on a Parallel Computer," 1997 IEEE 0-8186-8147-0/97, pp. 284-288. | |

23 | Mavris et al., "A Probabilistic Approach to Multivariate Constrained Robust Design Simulation," Society of Automotive Engineers, Inc., Paper No. 975508, 1997, pp. 1-11. | |

24 | National Institute of Health, "10-year CVD Risk Calculator" available at http://hin.nhlbi.nih.gov/atpiii/calculator.asp?usertype=prof, printed Aug. 2, 2005, 2 pages. | |

25 | Obayashi et al, "Multiobjective Evolutionary Computation for Supersonic Wing-Shape Optimization," IEEE Transactions on Evolutionary Computation, vol. 4, No. 2, Jul. 2000, pp. 182-187. | |

26 | Simpson et al., "Metamodels for Computer-Based Engineering Design: Survey & Recommendations," Engineering with Computers, 2001, vol. 17, pp. 129-150. | |

27 | Song et al., "The Hyperellipsoidal Clustering Using Genetic Algorithm," 1997 IEEE International Conference on Intelligent Processing Systems, Oct. 28-31, 1997, Beijing, China, pp. 592-596. | |

28 | Sytsma, Sid, "Quality and Statistical Process Control," available at http://www.sytsma.com/tqmtools/ctlchtprinciples.html, printed Apr. 7, 2005, 6 pages. | |

29 | Taguchi et al., "The Mahalanobis-Taguchi Strategy," A Pattern Technology System, John Wiley & Sons, Inc., 2002, 234 pages. | |

30 | Taylor et al., "Guidelines for Evaluating and Expressing the Uncertainty of NIST Measurement Results," NIST Technical Note 1297, 1994 Edition, United States Dept. of Commerce, National Institute of Standards and Technology (25 pages). | |

31 | Thompson, G.J. et al., "Neural Network Modelling of the Emissions and Performance of a Heavy-Duty Diesel Engine," Proc. Instu. Mech. Engrs., vol. 214, Part D (2000), pp. 111-126. | |

32 | Traver, Michael L. et al., "A Neural Network-Based Virtual NOx Sensor for Diesel Engines," West Virginia University, Mechanical and Aerospace Engineering Dept., Morgantown, WV 26506-6101, 6106, 7 pages, 1999. | |

33 | Traver, Michael L. et al., "Neural Network-Based Diesel Engine Emissions Prediction Using In-Cylinder Combustion Pressure," International Spring Fuels & Lubricants Meeting & Exposition, SAE Technical Paper Series, May 3-6, 1999, 17 pages. | |

34 | Woodall, et al., "A Review and Analysis of the Mahalanobis-Taguchi System," Technometrics, Feb. 2003, vol. 45, No. 1 (15 pages). | |

35 | Wu et al., "Cam-phasing Optimization Using Artificial Neural Networks as Surrogate Models-Fuel Consumption and Nox Emissions," SAE Technical Paper Series, 2006-01-1512, Apr. 3-6, 2006 (19 pages). | |

36 | Wu et al., "Cam-phasing Optimization Using Artificial Neural Networks as Surrogate Models—Fuel Consumption and Nox Emissions," SAE Technical Paper Series, 2006-01-1512, Apr. 3-6, 2006 (19 pages). | |

37 | Yang et al., "Similar Cases Retrieval from the Database of Laboratory Test Results," Journal of Medical Systems, vol. 27, No. 3, Jun. 2003, pp. 271-282. | |

38 | Yuan et al., "Evolutionary Fuzzy C-Means Clustering Algorithm," 1995 IEEE 0-7803-2461-7/95, pp. 2221-2226. |

Referenced by

Citing Patent | Filing date | Publication date | Applicant | Title |
---|---|---|---|---|

US8755923 * | 7 Dec 2010 | 17 Jun 2014 | Engineering Technology Associates, Inc. | Optimization system |

US9659111 * | 21 Mar 2014 | 23 May 2017 | The Procter & Gamble Company | Method for designing a material processing system |

US20110137443 * | 7 Dec 2010 | 9 Jun 2011 | Akbar Farahani | Design Optimization System |

US20150269283 * | 21 Mar 2014 | 24 Sep 2015 | The Procter & Gamble Company | Method for Designing a Material Processing System |

US20160004792 * | 7 Jul 2014 | 7 Jan 2016 | The Procter & Gamble Company | Method for designing an assembled product and product assembly system |

Classifications

U.S. Classification | 703/2, 703/1 |

International Classification | G06F7/60, G06F17/10 |

Cooperative Classification | G06F2217/08, G06F2217/06, G06F17/50, G06F2217/10 |

European Classification | G06F17/50 |

Legal Events

Date | Code | Event | Description |
---|---|---|---|

17 Dec 2008 | AS | Assignment | Owner name: CATERPILLAR INC., ILLINOIS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GRICHNIK, ANTHONY J.;SESKIN, MICHAEL X;MASON, JAMES R.;AND OTHERS;REEL/FRAME:022058/0564;SIGNING DATES FROM 20081120 TO 20081125 Owner name: CATERPILLAR INC., ILLINOIS Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:GRICHNIK, ANTHONY J.;SESKIN, MICHAEL X;MASON, JAMES R.;AND OTHERS;SIGNING DATES FROM 20081120 TO 20081125;REEL/FRAME:022058/0564 |

24 Nov 2015 | FPAY | Fee payment | Year of fee payment: 4 |

Rotate